What shells does MCP Shell Server support?
It supports bash, zsh, fish, powershell, cmd, and others. You can specify a custom shell path with the `-s` or `--shell` argument when starting the server.
@MCP-Mirror
基本信息
Mirror of
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"mkusaka_mcp-shell-server": {
"command": "node",
"args": [
"dist/index.js"
]
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
MCP Shell Server is a bridge that uses the Model Context Protocol (MCP) to allow AI agents to safely execute shell commands. It supports single-line and multi-line commands across multiple shells and is designed for integration with AI assistants like Cursor.
Install globally via npm, yarn, or pnpm, then add the server to your MCP configuration (e.g., in Cursor's ~/.cursor/config.json). The server provides a shell_exec tool that accepts a required command string. You can also specify a custom shell using the -s or --shell command-line argument.
It supports bash, zsh, fish, powershell, cmd, and others. You can specify a custom shell path with the `-s` or `--shell` argument when starting the server.
The `command` parameter is required and must be a string containing the shell command to execute.
Install it globally: `npm install -g @mkusaka/mcp-shell-server`, `yarn global add @mkusaka/mcp-shell-server`, or `pnpm add -g @mkusaka/mcp-shell-server`.
It exposes `hostname://`, `platform://`, `shell://`, `username://`, and `system-info://` (which returns hostname, platform, shell, username, CPU count, total/free memory, and uptime).
Yes, it supports both powershell and cmd in addition to Unix shells like bash and zsh.

Public read-only MCP server for discovering, inspecting, installing, and sharing approved Codex-compatible animated pet packs.

Agent-Native Terminal

Automated codebase documentation for GitHub: searchable docs, MCP context for AI agents, doc drift detection, and Friday Cleanup PRs.

ArtiBot Cloud MCP (Zhijiangyun 智匠云) — cloud MCP server for robot manipulation data & GPU workloads. 15 tools: robot fleet management, data collection & video recording, post-processing pipelines, and benchmark evaluation

MCP server for AI Agents — exposes Yocoolab feedback threads and design selections as tools
评论